Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the behavioral burden; it does disclose a critical nontrivial trait ('operation fails if the destination path already exists'), which is genuinely valuable for an agent. However, it leaves other behaviors undisclosed, such as whether intermediate directories are created, what the call returns on success, and whether source metadata/permissions are preserved.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with zero waste: the first states the purpose, and the second front-loads a critical failure condition with an IMPORTANT marker. Every sentence earns its place and the most decision-relevant constraint is highly visible.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description could reasonably explain what a successful copy returns or confirms, but does not. The critical correctness details (recursive requirement, destination naming, failure-on-existing) are covered across the description and full-coverage schema, leaving only minor edge-behavior gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline of 3 applies; the description itself adds no parameter-level detail. The schema already documents the important constraints (dst_path must include the target name, recursive must be true for directories), so no compensation is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Copies') and resource ('file or directory to a new location'), making the core purpose immediately clear. It differentiates from the closest sibling `move` through the verb itself, but does not explicitly name or contrast against `move` or `write`, so it falls short of the strongest sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use `copy` versus its most similar sibling `move` (e.g., use copy when the original must be preserved, move when it should be relocated), nor does it mention any alternatives for file creation like `write`. The only guidance present is operational (fails if destination exists), not usage routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of explaining behavior, and it does convey exact matching and modification of an existing file. It does not mention the failure on multiple matches or the replace_all default, though the parameter descriptions do cover those details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler. The core action is front-loaded and the usage context is presented efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has four parameters, complete schema descriptions, and no output schema. The description plus schema give an agent enough to call the tool correctly, though a brief behavioral warning about multiple matches would make it fully self-contained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The parameter descriptions already explain exact whitespace matching, line-number stripping, and replace_all behavior, so the main description does not need to add parameter-level detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb, resource, and mechanism: exact string replacement in a file. It also clarifies that the tool is for partial changes, which distinguishes it from siblings like write and remove.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'Useful for making partial changes to an existing file' gives clear context for when to use the tool, and implies it is not for full-file writes. However, it does not explicitly name alternatives or exclusion cases, so it stops short of full guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the search and sorting behavior, but omits the key fact that patterns are recursive by default (only documented in the schema). It also doesn't mention that it's a read-only operation, though that is implied. The recursion behavior is a significant surprise that should be highlighted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with zero waste. It starts with the verb and resource and includes the key behavior (sorting). Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 4 parameters and no annotations, the description is adequate but misses the default recursive pattern behavior, which is a critical invocation detail. It also doesn't hint at pagination or token-overflow concerns, though those are covered in the schema. It's not incomplete enough to be a 2, but it leaves room for more.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all parameters are well-documented in the schema. The tool description adds no additional parameter meaning beyond what the schema already provides, meeting the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb (searches), resource (files or directories), and a distinguishing behavior (sorted by modification time). It is specific enough to differentiate from sibling tools like grep (content search) and read/write operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description conveys clear context for what the tool does but does not explicitly mention when to use it versus alternatives or provide exclusions. An agent can infer it's for path-pattern discovery, but there's no explicit routing like 'use grep for content search'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only states that the tool searches, but does not disclose that it is read-only, what output format to expect, or any side effects. This is a notable gap for a tool with no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no filler. It front-loads the core purpose and method, making it easy to parse quickly. Every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 10 parameters, no output schema, and no annotations, the description is incomplete. It does not explain return values, line formatting, or why an agent should choose this over read or glob. The schema compensates for parameters, but the behavioral and output context is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameters are fully documented in the schema. The description adds no additional parameter semantics, and the baseline of 3 is appropriate since the schema already handles the definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Searches'), resource ('file contents'), and method ('using regular expressions'). This clearly differentiates grep from sibling tools like read (reading full contents) and glob (matching file paths).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use grep versus alternatives. The description does not mention conditions, exclusions, or sibling tools such as read or glob. An agent must infer usage solely from the purpose statement, which is not enough for clear tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the basic action of creating a directory and mentions the write tool's behavior, but does not disclose error conditions (e.g., what happens if the directory exists when parents is false), permission requirements, or return behavior. This is a significant gap for a tool with no annotation support.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise—two sentences, with the primary purpose front-loaded and the important usage note following. Every sentence earns its place, with no waste. It is appropriately sized for a simple tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool, the description is fairly complete. It covers the core action and includes a valuable note about the write tool's behavior to avoid redundancy. However, it omits details about error handling (e.g., behavior when the directory already exists) and does not describe return values, though the schema partially covers error behavior via the 'parents' flag. Overall, it is adequate for typical usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for both parameters, including default behavior for 'parents'. The description adds no additional parameter semantics beyond what the schema already provides. The baseline of 3 applies because the schema fully documents the parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb and resource: 'Creates a new directory.' It is specific and unambiguous, distinguishing itself from siblings like write, read, and remove by its directory-focused action. However, it does not explicitly contrast itself with sibling tools beyond the write tool note, so it lacks full differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells agents when NOT to use mkdir: 'You DO NOT need to call mkdir prior to writing a new file with the write tool.' This is a strong usage exclusion that prevents unnecessary calls. It does not explicitly state when to use it, but the purpose is clear enough that usage is implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It does warn that an existing destination will be overwritten, which is a critical destructive behavior. However, it does not disclose other relevant behaviors such as what happens on failure, whether it returns anything, permission requirements, or whether moving a directory moves its contents recursively. The overwrite warning is valuable but the disclosure is incomplete for a mutation tool without annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two sentences. The first states the purpose directly, and the second highlights the critical overwrite warning, which is front-loaded and prominent. There is no fluff or redundant content, and every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (two parameters, no output schema, no annotations), the description covers the most essential safety aspect (overwrite) but lacks detail on return values, error handling, and edge cases like moving directories. For an agent to use it safely, the overwrite warning is key, but other aspects like what happens on success are unspecified. It is adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for both parameters. The src_path description is clear, and the dst_path description includes an important note about including the target name, which adds value beyond the schema. The tool description itself contributes no additional parameter information, so the baseline of 3 applies because the schema already handles semantics well.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Moves or renames a file or directory.' It clearly indicates the operation's scope and is distinct from siblings like copy (duplicates) and remove (deletes), though it does not explicitly name alternatives. The verb 'move' inherently differentiates it, but the description doesn't call out sibling distinctions, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives. It does not mention 'use copy for duplication' or 'use remove for deletion,' nor does it specify any prerequisites or conditions. The only additional instruction is a caution to verify the destination path, which is not usage selection guidance. The intended use is implied by the verb but not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It states only the action and supported types, but does not disclose that read is non-destructive, whether it requires permissions, or how it handles large files or media output. The description adds no behavioral context beyond the basic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise, with two short sentences. The first sentence states the core action; the second clarifies support for media files, which is non-obvious and adds value. It is front-loaded and efficient, though it could be slightly more informative without losing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the rich schema (100% parameter coverage) and no output schema, the description is adequate for basic understanding but lacks details on media file behavior and output format. The mention of 'media files' is ambiguous—does it return binary data or a preview? The description does not clarify, so completeness is only moderate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all parameters (path, type, limit, offset, show_line_numbers) are already well-documented. The description adds no parameter information beyond what the schema provides. Per the rubric, the baseline is 3 when schema covers all parameters, and the description does not improve on it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Reads') and resource ('the contents of a file'), and the mention of text/media files distinguishes it from sibling tools like write, edit, and remove. The purpose is unambiguous and the agent can immediately infer this is a read operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. It does not mention that grep is for searching content, or that read is for retrieving file contents, nor any exclusions or prerequisites. An agent is left to infer usage from the purpose alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly warns that the action is permanent and instructs verifying the path, which is critical behavioral context for a destructive operation. It also notes that recursive must be true for non-empty directories, which is a key behavioral constraint. However, it doesn't mention what happens on failure (e.g., missing path) or whether it returns any confirmation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with zero waste. The core action is front-loaded, and the critical warning is placed immediately after. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive tool with no annotations and no output schema, the description covers the essential safety context (permanence, path verification, recursive requirement). It doesn't describe return values, but the absence of an output schema lowers the bar. It could mention error behavior (e.g., what happens if the path doesn't exist), but the critical operational details are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters. The description adds the critical warning that recursive MUST be true for non-empty directories, which reinforces the schema's own note. This adds some value beyond the schema, but the schema already covers the parameter meanings well, so a baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb ('Removes') and resource ('a file or directory'), which distinguishes it from siblings like copy, move, edit, and write. It doesn't explicitly name a sibling alternative, but the action is unambiguous and the scope is clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (when you want to delete a file or directory) but doesn't explicitly contrast it with alternatives like move (which could relocate instead of delete) or provide conditions for when not to use it. The permanent-destruction warning serves as a caution but not a usage guideline.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly says 'Gets information' which implies a read-only operation, and it lists the returned fields. However, it does not mention error behavior (e.g., if the path does not exist), whether it follows symbolic links, or any permission requirements. It adds useful return-value context but stops short of deeper behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, tight sentence with no filler. The core purpose is front-loaded ('Gets information about a file or directory'), followed by a specific list of returned attributes. Every word earns its place, and it is appropriately sized for a simple tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is sufficiently complete for a one-parameter tool with no output schema. It enumerates the key data an agent would expect from a stat operation. It does not cover error cases or symlink behavior, but for a standard metadata retrieval tool, the provided list of return fields is adequate for an agent to know what to expect. Minor gaps exist, but they do not undermine usability.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully documents the sole parameter 'path' with a clear description. Since schema description coverage is 100%, the tool description adds no additional parameter semantics. The baseline of 3 applies because the schema already carries the load; the description does not need to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it gets information about a file or directory and enumerates specific attributes (file type, size, times, permissions). This is a specific verb+resource that distinguishes it from siblings like read (content), write, edit, and remove. An agent can immediately understand what this tool does and how it differs from the rest.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus alternatives. The description simply states its function without mentioning any prerequisites, exclusions, or scenarios where another tool would be more appropriate. The distinction from siblings is implied by its name and purpose, but not articulated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly discloses the destructive overwrite behavior and the side effect of creating parent directories. It also adds a caution about data loss, which is valuable transparency beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely tight: the first sentence states the core action, the second clarifies overwrite behavior, and the final paragraph adds an important warning and sibling alternative. No word is wasted, and the key facts are front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter write tool with no output schema or annotations, the description covers the essential context: purpose, overwrite/destructive behavior, parent directory creation, and guidance for using the alternative `edit` tool. It doesn't detail error cases, but the information needed to invoke it correctly is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds meaning by stating that missing parent directories are automatically created (path behavior) and that content is the complete replacement, reinforcing that partial changes should go to `edit`. This goes beyond the schema's simple descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it writes a file, automatically creates missing parent directories, and overwrites existing files. It explicitly distinguishes itself from the `edit` tool by directing partial changes elsewhere, so an agent can tell them apart immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-not guidance: for partial changes to existing files, prefer the `edit` tool. It also warns to ensure complete file context before modifying existing files, which is a clear usage prerequisite.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.